![](https://img-blog.csdnimg.cn/20201014180756928.png?x-oss-process=image/resize,m_fixed,h_64,w_64)
文献阅读笔记
文章平均质量分 69
文献阅读笔记
nightluo
愿时光能缓,故人不散,愿独闯的日子里不惧孤单!
展开
-
Detecting Everything in the Open World: Towards Universal Object Detection
在 Open World 中检测一切:面向通用目标检测。原创 2023-03-27 20:38:18 · 1483 阅读 · 0 评论 -
ML-Decoder: Scalable and Versatile Classification Head
可扩展和通用的分类头。原创 2023-03-19 21:32:44 · 653 阅读 · 1 评论 -
Asymmetric Loss for Multi-Label Classification
多标签分类的不对称损失。原创 2023-03-19 18:41:50 · 453 阅读 · 0 评论 -
CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images
1、在大规模弱监督网络网络图像上训练深度神经网络,图像为关键词索引的、没有任何人工注释的互联网图像,通过利用课程学习来制定学习策略以有效处理大量噪声标签和数据不均衡问题2、设计新的学习课程:通过在特征空间使用数据的分布密度来测量数据的复杂性,并以无监督的方式对复杂性进行排序,允许通过直接搜索高噪声标签,以实施有效的课程学习策略3、目的:提供一种能够有效处理大量噪声标签和数据不平衡的解决方案,通过利用课程学习来开发一种简单但高效的训练策略,通过利用高噪声标签来提高标准深度网络的模型泛化和整体能力。原创 2023-01-08 23:09:56 · 239 阅读 · 0 评论 -
Curriculum Learning
1、训练策略形式化,显著提高泛化能力,更快的收敛速度2、假设:精心选择的课程策略可以作为一种连续方法(continuation method)——能够帮助找到更好的非凸训练准则的局部最小值3、实验证明,课程策略类似于正则器,增益效果在测试集上更为明显,可以加速训练收敛到全局最小值4、原创 2023-01-08 12:12:14 · 174 阅读 · 0 评论 -
Multi-Lable 数据集
The MS COCO (Microsoft Common Objects in Context) dataset is a large-scale object detection, segmentation, key-point detection, and captioning dataset. The dataset consists of 328K images.Annotations: The dataset has annotations forThe first version of MS原创 2023-01-05 10:22:54 · 444 阅读 · 0 评论 -
Global Meets Local: Effective Multi-Label Image Classification via Category-Aware Weak Supervision
Global Meets Local: Effective Multi-Label Image Classification via Category-Aware Weak Supervision, 2022原创 2022-12-19 21:58:38 · 287 阅读 · 1 评论 -
Learning Disentangled Label Representations for Multi-label Classification
Learning Disentangled Label Representations for Multi-label Classification,2022原创 2022-12-19 21:41:42 · 634 阅读 · 1 评论 -
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence, NIPS, 2020原创 2022-12-19 20:27:55 · 706 阅读 · 0 评论 -
Semi-Supervised Classification with Graph Convolutional Networks
Semi-Supervised Classification with Graph Convolutional Networks, ICLR, 2017原创 2022-12-08 23:20:01 · 586 阅读 · 0 评论 -
Label 相关论文汇总
Label相关的论文汇总原创 2022-11-23 15:28:03 · 1412 阅读 · 0 评论